© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11851
    Prev
    Next
    INDEX
    Explanations

    http and https links

    np_acts-logits-general · gemini-2.5-flash-lite

    URLs and technical formatting elements in programming or mathematical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     for
    -2.42
     at
    -1.79
     three
    -1.66
     two
    -1.54
     first
    -1.49
     in
    -1.48
     For
    -1.46
    You
    -1.43
     (
    -1.41
     Because
    -1.40
    POSITIVE LOGITS
    </strong>
    2.48
    </i>
    2.36
    </em>
    2.33
    </b>
    1.66
     CÓ
    1.58
    </h2>
    1.55
     tivi
    1.55
    despite
    1.54
     tía
    1.48
    </tbody>
    1.48
    Activations Density 0.298%

    No Known Activations